Journal_Utilities/.env.example at main · ActiveInferenceInstitute/Journal_Utilities · GitHub

History

68 lines (59 loc) · 2.91 KB

Raw

# =============================================================================

# Journal Utilities - Environment Configuration

# =============================================================================

# This file contains all environment variables needed for both the transcription

# pipeline (WhisperX) and entity extraction pipeline (journal_utilities.rag / Cohere)

# =============================================================================

# Copy to `.env` and fill in real values. Never commit a real `.env` file.

# -----------------------------------------------------------------------------

# Application Settings

# -----------------------------------------------------------------------------

APP_NAME=Journal-Utilities

VERSION=0.1.0

DEBUG=False

# -----------------------------------------------------------------------------

# Transcription Pipeline (WhisperX)

# -----------------------------------------------------------------------------

# Hugging Face token for WhisperX diarization models

# Get from: https://huggingface.co/settings/tokens

# Required models: pyannote/segmentation-3.0, pyannote/speaker-diarization-3.1

# `transcribe_worklist.py` accepts either name; the legacy WhisperX pipeline

# (`transcribe/transcribe.py`) reads `HF_TOKEN`.

HUGGINGFACE_TOKEN=your_huggingface_token_here

HF_TOKEN=your_huggingface_token_here

# Coda API Token for fetching session data

# Get from: https://coda.io/account (API settings section)

CODA_API_TOKEN=your_coda_api_token_here

# Legacy WhisperX pipeline directories (transcribe/transcribe.py only —

# the modern workflow is scripts/transcribe_worklist.py + the journal repo)

WAV_DIRECTORY=/path/to/audio/wavs

OUTPUT_DIR=/path/to/project/data/output

# -----------------------------------------------------------------------------

# Entity Extraction Pipeline (journal_utilities.rag / Cohere)

# -----------------------------------------------------------------------------

# Cohere API Configuration for entity extraction

# Get from: https://dashboard.cohere.com/api-keys

COHERE_API_KEY=your_cohere_api_key_here

COHERE_MODEL=command-a-03-2025

# Processing settings for entity extraction

BATCH_SIZE=10

MAX_RETRIES=3

# -----------------------------------------------------------------------------

# SurrealDB Configuration (shared by both pipelines)

# -----------------------------------------------------------------------------

# Database connection settings

# `journal_utilities.data` uses the DB_* prefix; `journal_utilities.rag`

# settings use the SURREALDB_* prefix. Both are read from the environment.

# Primary configuration (used by journal_utilities.data)

DB_URL=ws://0.0.0.0:8080/rpc

DB_USER=root

DB_PASSWORD=root

DB_NAME=actinf

DB_NAMESPACE=actinf

# Alternative configuration (used by journal_utilities.rag)

# Set to the same values as above for consistency

SURREALDB_URL=ws://0.0.0.0:8080/rpc

SURREALDB_USERNAME=root

SURREALDB_PASSWORD=root

SURREALDB_DATABASE=actinf

SURREALDB_NAMESPACE=actinf

Journal_Utilities/.env.example at main · ActiveInferenceInstitute/Journal_Utilities · GitHub

Expand file tree

Breadcrumbs

.env.example

Latest commit

History

Breadcrumbs

.env.example

File metadata and controls